Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roying
    -0.72
     [];
    -0.67
    ufact
    -0.63
    resent
    -0.62
    regor
    -0.62
    hov
    -0.62
    forming
    -0.60
    finding
    -0.60
    rentice
    -0.59
    Transfer
    -0.59
    POSITIVE LOGITS
     sights
    1.26
     own
    1.25
     doubts
    1.06
     eyes
    0.89
     fingerprints
    0.88
     tentacles
    0.84
     suspicions
    0.83
     ups
    0.83
     fingers
    0.83
     faults
    0.80
    Act Density 0.077%

    No Known Activations